Title :
Application of neural networks in detecting hyperellipsoidal shells
Author :
Su, Mu-Chun ; Liu, I-Chen
Author_Institution :
Dept. of Electr. Eng., Tamkang Univ., Tamsui, Taiwan
Abstract :
This paper presents a novel class of neural networks which can be trained in an unsupervised manner to detect a mixture of hyperellipsoidal shells and/or segment of hyperellipsoidal shells. This approach is computationally and implementationally simpler than other clustering algorithms that have been suggested for this purpose. Experimental results are given to show the effectiveness of the proposed method
Keywords :
computational complexity; image recognition; neural nets; pattern clustering; unsupervised learning; clustering algorithms; computational complexity; hyperellipsoidal shell detection; neural networks; unsupervised training; Automatic frequency control; Clustering algorithms; Clustering methods; Computer vision; Digital images; Electronic mail; Extraterrestrial measurements; Intelligent networks; Neural networks; Shape measurement;
Conference_Titel :
Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4778-1
DOI :
10.1109/ICSMC.1998.728152
